Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg11_rand_seed_265358_test_samples_None_train_samples_None_weight_decay_0.01.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09116753190755844
Inter Cos: 0.10967151820659637
Norm Quadratic Average: 23.567670822143555
Nearest Class Center Accuracy: 0.8079833333333334

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10107233375310898
Inter Cos: 0.10701501369476318
Norm Quadratic Average: 2.342414379119873
Nearest Class Center Accuracy: 0.8531166666666666

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17868536710739136
Inter Cos: 0.1402253955602646
Norm Quadratic Average: 1.160029649734497
Nearest Class Center Accuracy: 0.9111833333333333

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.233073428273201
Inter Cos: 0.1647304892539978
Norm Quadratic Average: 0.7089022994041443
Nearest Class Center Accuracy: 0.95265

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3093859851360321
Inter Cos: 0.13434694707393646
Norm Quadratic Average: 0.31527018547058105
Nearest Class Center Accuracy: 0.98935

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6785291433334351
Inter Cos: 0.2225033938884735
Norm Quadratic Average: 0.28968346118927
Nearest Class Center Accuracy: 0.9994

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8796117901802063
Inter Cos: 0.2195727378129959
Norm Quadratic Average: 0.44730904698371887
Nearest Class Center Accuracy: 1.0

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9836410284042358
Inter Cos: 0.2725749909877777
Norm Quadratic Average: 0.870271623134613
Nearest Class Center Accuracy: 1.0

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.037280559539795
Linear Weight Rank: 8
Intra Cos: 0.9968439936637878
Inter Cos: 0.29068949818611145
Norm Quadratic Average: 23.208120346069336
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.0382704734802246
Linear Weight Rank: 1287
Intra Cos: 0.997760534286499
Inter Cos: 0.25723323225975037
Norm Quadratic Average: 16.52345848083496
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.039304494857788
Linear Weight Rank: 8
Intra Cos: 0.9983546137809753
Inter Cos: 0.21042652428150177
Norm Quadratic Average: 12.022582054138184
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9982298016548157
Inter Cos: 0.2409406155347824
Norm Quadratic Average: 9.400938034057617
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.01830083345770836
Accuracy: 0.9959
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.0361921563744545, Weights: 0.011056958697736263
NC2 Equiangle: Features: 0.169800779554579, Weights: 0.16672371758355034
NC3 Self-Duality: 0.035907234996557236
NC4 NCC Mismatch: 0.0006000000000000449

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10219583660364151
Inter Cos: 0.12048852443695068
Norm Quadratic Average: 23.595197677612305
Nearest Class Center Accuracy: 0.8229

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11121582239866257
Inter Cos: 0.10739607363939285
Norm Quadratic Average: 2.3303868770599365
Nearest Class Center Accuracy: 0.8655

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19038136303424835
Inter Cos: 0.13816426694393158
Norm Quadratic Average: 1.1545469760894775
Nearest Class Center Accuracy: 0.9193

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.24538537859916687
Inter Cos: 0.1613939255475998
Norm Quadratic Average: 0.707385778427124
Nearest Class Center Accuracy: 0.9555

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3226410746574402
Inter Cos: 0.1503353714942932
Norm Quadratic Average: 0.3145667314529419
Nearest Class Center Accuracy: 0.9873

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6802526712417603
Inter Cos: 0.23455634713172913
Norm Quadratic Average: 0.2896518409252167
Nearest Class Center Accuracy: 0.9935

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8706303238868713
Inter Cos: 0.21919947862625122
Norm Quadratic Average: 0.4466555714607239
Nearest Class Center Accuracy: 0.9953

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.968928337097168
Inter Cos: 0.271060973405838
Norm Quadratic Average: 0.8662084937095642
Nearest Class Center Accuracy: 0.9959

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.037280559539795
Linear Weight Rank: 8
Intra Cos: 0.979847252368927
Inter Cos: 0.2927658259868622
Norm Quadratic Average: 23.091171264648438
Nearest Class Center Accuracy: 0.9959

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.0382704734802246
Linear Weight Rank: 1287
Intra Cos: 0.9816556572914124
Inter Cos: 0.2552957832813263
Norm Quadratic Average: 16.43741226196289
Nearest Class Center Accuracy: 0.9959

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.039304494857788
Linear Weight Rank: 8
Intra Cos: 0.9824577569961548
Inter Cos: 0.2092759907245636
Norm Quadratic Average: 11.958179473876953
Nearest Class Center Accuracy: 0.9959

Output Layer:
Intra Cos: 0.9839279055595398
Inter Cos: 0.23764464259147644
Norm Quadratic Average: 9.3494873046875
Nearest Class Center Accuracy: 0.9959

